Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    profane language related to the buttocks

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "ass."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kubrick
    -0.71
    MSN
    -0.65
    _-
    -0.64
    Interested
    -0.63
     scarce
    -0.61
     Canaver
    -0.59
     Petersen
    -0.59
     Stras
    -0.59
    APH
    -0.57
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.57
    POSITIVE LOGITS
    imilation
    1.47
    holes
    1.34
     cheeks
    1.13
    asin
    1.11
    ortment
    1.00
    itude
    1.00
    ailable
    0.96
    sembly
    0.96
    itance
    0.95
    ails
    0.90
    Act Density 0.018%

    No Known Activations